/* Size of buffers used for snprintfs. */
#define MAX_PRINT_BUFF 6072
-/* Maximum character device basename size. */
-#define MAX_BASENAME_SZ 10
-
/* Maximum long option length for option parsing. */
#define MAX_LONG_OPT_SZ 64
static struct rte_mempool *mbuf_pool;
static int mergeable;
-/* Do vlan strip on host, enabled on default */
-static uint32_t vlan_strip = 1;
-
/* Enable VM2VM communications. If this is disabled then the MAC address compare is skipped. */
typedef enum {
VM2VM_DISABLED = 0,
/* Disable TSO offload */
static uint32_t enable_tso;
+static int client_mode;
+static int dequeue_zero_copy;
+
/* Specify timeout (in useconds) between retries on RX. */
static uint32_t burst_rx_delay_time = BURST_RX_WAIT_US;
/* Specify the number of retries on RX. */
static uint32_t burst_rx_retry_num = BURST_RX_RETRIES;
-/* Character device basename. Can be set by user. */
-static char dev_basename[MAX_BASENAME_SZ] = "vhost-net";
+/* Socket file paths. Can be set by user */
+static char *socket_files;
+static int nb_sockets;
/* empty vmdq configuration structure. Filled in programatically */
static struct rte_eth_conf vmdq_conf_default = {
/* TX queue for each data core. */
struct mbuf_table lcore_tx_queue[RTE_MAX_LCORE];
+#define MBUF_TABLE_DRAIN_TSC ((rte_get_tsc_hz() + US_PER_S - 1) \
+ / US_PER_S * BURST_TX_DRAIN_US)
#define VLAN_HLEN 4
-/* Per-device statistics struct */
-struct device_statistics {
- uint64_t tx_total;
- rte_atomic64_t rx_total_atomic;
- uint64_t tx;
- rte_atomic64_t rx_atomic;
-} __rte_cache_aligned;
-struct device_statistics dev_statistics[MAX_DEVICES];
-
/*
* Builds up the correct configuration for VMDQ VLAN pool map
* according to the pool & queue limits.
rx_ring_size = RTE_TEST_RX_DESC_DEFAULT;
tx_ring_size = RTE_TEST_TX_DESC_DEFAULT;
+
+ /*
+ * When dequeue zero copy is enabled, guest Tx used vring will be
+ * updated only when corresponding mbuf is freed. Thus, the nb_tx_desc
+ * (tx_ring_size here) must be small enough so that the driver will
+ * hit the free threshold easily and free mbufs timely. Otherwise,
+ * guest Tx vring would be starved.
+ */
+ if (dequeue_zero_copy)
+ tx_ring_size = 64;
+
tx_rings = (uint16_t)rte_lcore_count();
retval = validate_num_devices(MAX_DEVICES);
if (enable_tso == 0) {
rte_vhost_feature_disable(1ULL << VIRTIO_NET_F_HOST_TSO4);
rte_vhost_feature_disable(1ULL << VIRTIO_NET_F_HOST_TSO6);
+ rte_vhost_feature_disable(1ULL << VIRTIO_NET_F_GUEST_TSO4);
+ rte_vhost_feature_disable(1ULL << VIRTIO_NET_F_GUEST_TSO6);
}
rx_rings = (uint16_t)dev_info.max_rx_queues;
/* Configure ethernet device. */
retval = rte_eth_dev_configure(port, rx_rings, tx_rings, &port_conf);
- if (retval != 0)
+ if (retval != 0) {
+ RTE_LOG(ERR, VHOST_PORT, "Failed to configure port %u: %s.\n",
+ port, strerror(-retval));
return retval;
+ }
/* Setup the queues. */
for (q = 0; q < rx_rings; q ++) {
rte_eth_dev_socket_id(port),
rxconf,
mbuf_pool);
- if (retval < 0)
+ if (retval < 0) {
+ RTE_LOG(ERR, VHOST_PORT,
+ "Failed to setup rx queue %u of port %u: %s.\n",
+ q, port, strerror(-retval));
return retval;
+ }
}
for (q = 0; q < tx_rings; q ++) {
retval = rte_eth_tx_queue_setup(port, q, tx_ring_size,
rte_eth_dev_socket_id(port),
txconf);
- if (retval < 0)
+ if (retval < 0) {
+ RTE_LOG(ERR, VHOST_PORT,
+ "Failed to setup tx queue %u of port %u: %s.\n",
+ q, port, strerror(-retval));
return retval;
+ }
}
/* Start the device. */
retval = rte_eth_dev_start(port);
if (retval < 0) {
- RTE_LOG(ERR, VHOST_DATA, "Failed to start the device.\n");
+ RTE_LOG(ERR, VHOST_PORT, "Failed to start port %u: %s\n",
+ port, strerror(-retval));
return retval;
}
}
/*
- * Set character device basename.
+ * Set socket file path.
*/
static int
-us_vhost_parse_basename(const char *q_arg)
+us_vhost_parse_socket_path(const char *q_arg)
{
/* parse number string */
-
- if (strnlen(q_arg, MAX_BASENAME_SZ) > MAX_BASENAME_SZ)
+ if (strnlen(q_arg, PATH_MAX) > PATH_MAX)
return -1;
- else
- snprintf((char*)&dev_basename, MAX_BASENAME_SZ, "%s", q_arg);
+
+ socket_files = realloc(socket_files, PATH_MAX * (nb_sockets + 1));
+ snprintf(socket_files + nb_sockets * PATH_MAX, PATH_MAX, "%s", q_arg);
+ nb_sockets++;
return 0;
}
RTE_LOG(INFO, VHOST_CONFIG, "%s [EAL options] -- -p PORTMASK\n"
" --vm2vm [0|1|2]\n"
" --rx_retry [0|1] --mergeable [0|1] --stats [0-N]\n"
- " --dev-basename <name>\n"
+ " --socket-file <path>\n"
" --nb-devices ND\n"
" -p PORTMASK: Set mask for ports to be used by application\n"
" --vm2vm [0|1|2]: disable/software(default)/hardware vm2vm comms\n"
" --rx-retry-delay [0-N]: timeout(in usecond) between retries on RX. This makes effect only if retries on rx enabled\n"
" --rx-retry-num [0-N]: the number of retries on rx. This makes effect only if retries on rx enabled\n"
" --mergeable [0|1]: disable(default)/enable RX mergeable buffers\n"
- " --vlan-strip [0|1]: disable/enable(default) RX VLAN strip on host\n"
" --stats [0-N]: 0: Disable stats, N: Time in seconds to print stats\n"
- " --dev-basename: The basename to be used for the character device.\n"
+ " --socket-file: The path of the socket file.\n"
" --tx-csum [0|1] disable/enable TX checksum offload.\n"
- " --tso [0|1] disable/enable TCP segment offload.\n",
+ " --tso [0|1] disable/enable TCP segment offload.\n"
+ " --client register a vhost-user socket as client mode.\n"
+ " --dequeue-zero-copy enables dequeue zero copy\n",
prgname);
}
{"rx-retry-delay", required_argument, NULL, 0},
{"rx-retry-num", required_argument, NULL, 0},
{"mergeable", required_argument, NULL, 0},
- {"vlan-strip", required_argument, NULL, 0},
{"stats", required_argument, NULL, 0},
- {"dev-basename", required_argument, NULL, 0},
+ {"socket-file", required_argument, NULL, 0},
{"tx-csum", required_argument, NULL, 0},
{"tso", required_argument, NULL, 0},
+ {"client", no_argument, &client_mode, 1},
+ {"dequeue-zero-copy", no_argument, &dequeue_zero_copy, 1},
{NULL, 0, 0, 0},
};
}
}
- /* Enable/disable RX VLAN strip on host. */
- if (!strncmp(long_option[option_index].name,
- "vlan-strip", MAX_LONG_OPT_SZ)) {
- ret = parse_num_opt(optarg, 1);
- if (ret == -1) {
- RTE_LOG(INFO, VHOST_CONFIG,
- "Invalid argument for VLAN strip [0|1]\n");
- us_vhost_usage(prgname);
- return -1;
- } else {
- vlan_strip = !!ret;
- vmdq_conf_default.rxmode.hw_vlan_strip =
- vlan_strip;
- }
- }
-
/* Enable/disable stats. */
if (!strncmp(long_option[option_index].name, "stats", MAX_LONG_OPT_SZ)) {
ret = parse_num_opt(optarg, INT32_MAX);
if (ret == -1) {
- RTE_LOG(INFO, VHOST_CONFIG, "Invalid argument for stats [0..N]\n");
+ RTE_LOG(INFO, VHOST_CONFIG,
+ "Invalid argument for stats [0..N]\n");
us_vhost_usage(prgname);
return -1;
} else {
}
}
- /* Set character device basename. */
- if (!strncmp(long_option[option_index].name, "dev-basename", MAX_LONG_OPT_SZ)) {
- if (us_vhost_parse_basename(optarg) == -1) {
- RTE_LOG(INFO, VHOST_CONFIG, "Invalid argument for character device basename (Max %d characters)\n", MAX_BASENAME_SZ);
+ /* Set socket file path. */
+ if (!strncmp(long_option[option_index].name,
+ "socket-file", MAX_LONG_OPT_SZ)) {
+ if (us_vhost_parse_socket_path(optarg) == -1) {
+ RTE_LOG(INFO, VHOST_CONFIG,
+ "Invalid argument for socket name (Max %d characters)\n",
+ PATH_MAX);
us_vhost_usage(prgname);
return -1;
}
{
struct vhost_dev *vdev;
- TAILQ_FOREACH(vdev, &vhost_dev_list, next) {
+ TAILQ_FOREACH(vdev, &vhost_dev_list, global_vdev_entry) {
if (vdev->ready == DEVICE_RX &&
is_same_ether_addr(mac, &vdev->mac_address))
return vdev;
link_vmdq(struct vhost_dev *vdev, struct rte_mbuf *m)
{
struct ether_hdr *pkt_hdr;
- struct virtio_net *dev = vdev->dev;
int i, ret;
/* Learn MAC address of guest device from packet */
if (find_vhost_dev(&pkt_hdr->s_addr)) {
RTE_LOG(ERR, VHOST_DATA,
- "Device (%" PRIu64 ") is using a registered MAC!\n",
- dev->device_fh);
+ "(%d) device is using a registered MAC!\n",
+ vdev->vid);
return -1;
}
vdev->mac_address.addr_bytes[i] = pkt_hdr->s_addr.addr_bytes[i];
/* vlan_tag currently uses the device_id. */
- vdev->vlan_tag = vlan_tags[dev->device_fh];
+ vdev->vlan_tag = vlan_tags[vdev->vid];
/* Print out VMDQ registration info. */
- RTE_LOG(INFO, VHOST_DATA, "(%"PRIu64") MAC_ADDRESS %02x:%02x:%02x:%02x:%02x:%02x and VLAN_TAG %d registered\n",
- dev->device_fh,
+ RTE_LOG(INFO, VHOST_DATA,
+ "(%d) mac %02x:%02x:%02x:%02x:%02x:%02x and vlan %d registered\n",
+ vdev->vid,
vdev->mac_address.addr_bytes[0], vdev->mac_address.addr_bytes[1],
vdev->mac_address.addr_bytes[2], vdev->mac_address.addr_bytes[3],
vdev->mac_address.addr_bytes[4], vdev->mac_address.addr_bytes[5],
/* Register the MAC address. */
ret = rte_eth_dev_mac_addr_add(ports[0], &vdev->mac_address,
- (uint32_t)dev->device_fh + vmdq_pool_base);
+ (uint32_t)vdev->vid + vmdq_pool_base);
if (ret)
- RTE_LOG(ERR, VHOST_DATA, "(%"PRIu64") Failed to add device MAC address to VMDQ\n",
- dev->device_fh);
+ RTE_LOG(ERR, VHOST_DATA,
+ "(%d) failed to add device MAC address to VMDQ\n",
+ vdev->vid);
- /* Enable stripping of the vlan tag as we handle routing. */
- if (vlan_strip)
- rte_eth_dev_set_vlan_strip_on_queue(ports[0],
- (uint16_t)vdev->vmdq_rx_q, 1);
+ rte_eth_dev_set_vlan_strip_on_queue(ports[0], vdev->vmdq_rx_q, 1);
/* Set device as ready for RX. */
vdev->ready = DEVICE_RX;
}
static inline void __attribute__((always_inline))
-virtio_xmit(struct virtio_net *dst_dev, struct virtio_net *src_dev,
+virtio_xmit(struct vhost_dev *dst_vdev, struct vhost_dev *src_vdev,
struct rte_mbuf *m)
{
uint16_t ret;
- ret = rte_vhost_enqueue_burst(dst_dev, VIRTIO_RXQ, &m, 1);
+ ret = rte_vhost_enqueue_burst(dst_vdev->vid, VIRTIO_RXQ, &m, 1);
if (enable_stats) {
- rte_atomic64_inc(&dev_statistics[dst_dev->device_fh].rx_total_atomic);
- rte_atomic64_add(&dev_statistics[dst_dev->device_fh].rx_atomic, ret);
- dev_statistics[src_dev->device_fh].tx_total++;
- dev_statistics[src_dev->device_fh].tx += ret;
+ rte_atomic64_inc(&dst_vdev->stats.rx_total_atomic);
+ rte_atomic64_add(&dst_vdev->stats.rx_atomic, ret);
+ src_vdev->stats.tx_total++;
+ src_vdev->stats.tx += ret;
}
}
{
struct ether_hdr *pkt_hdr;
struct vhost_dev *dst_vdev;
- uint64_t fh;
pkt_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *);
if (!dst_vdev)
return -1;
- fh = dst_vdev->dev->device_fh;
- if (fh == vdev->dev->device_fh) {
- RTE_LOG(DEBUG, VHOST_DATA,
- "(%" PRIu64 ") TX: src and dst MAC is same. "
- "Dropping packet.\n", fh);
+ if (vdev->vid == dst_vdev->vid) {
+ RTE_LOG_DP(DEBUG, VHOST_DATA,
+ "(%d) TX: src and dst MAC is same. Dropping packet.\n",
+ vdev->vid);
return 0;
}
- RTE_LOG(DEBUG, VHOST_DATA,
- "(%" PRIu64 ") TX: MAC address is local\n", fh);
+ RTE_LOG_DP(DEBUG, VHOST_DATA,
+ "(%d) TX: MAC address is local\n", dst_vdev->vid);
if (unlikely(dst_vdev->remove)) {
- RTE_LOG(DEBUG, VHOST_DATA, "(%" PRIu64 ") "
- "Device is marked for removal\n", fh);
+ RTE_LOG_DP(DEBUG, VHOST_DATA,
+ "(%d) device is marked for removal\n", dst_vdev->vid);
return 0;
}
- virtio_xmit(dst_vdev->dev, vdev->dev, m);
+ virtio_xmit(dst_vdev, vdev, m);
return 0;
}
* and get its vlan tag, and offset if it is.
*/
static inline int __attribute__((always_inline))
-find_local_dest(struct virtio_net *dev, struct rte_mbuf *m,
+find_local_dest(struct vhost_dev *vdev, struct rte_mbuf *m,
uint32_t *offset, uint16_t *vlan_tag)
{
struct vhost_dev *dst_vdev;
if (!dst_vdev)
return 0;
- if (dst_vdev->dev->device_fh == dev->device_fh) {
- RTE_LOG(DEBUG, VHOST_DATA,
- "(%" PRIu64 ") TX: src and dst MAC is same. "
- " Dropping packet.\n", dst_vdev->dev->device_fh);
+ if (vdev->vid == dst_vdev->vid) {
+ RTE_LOG_DP(DEBUG, VHOST_DATA,
+ "(%d) TX: src and dst MAC is same. Dropping packet.\n",
+ vdev->vid);
return -1;
}
* the packet length by plus it.
*/
*offset = VLAN_HLEN;
- *vlan_tag = vlan_tags[(uint16_t)dst_vdev->dev->device_fh];
+ *vlan_tag = vlan_tags[vdev->vid];
- RTE_LOG(DEBUG, VHOST_DATA,
- "(%" PRIu64 ") TX: pkt to local VM device id: (%" PRIu64 ") "
- "vlan tag: %u.\n",
- dev->device_fh, dst_vdev->dev->device_fh, *vlan_tag);
+ RTE_LOG_DP(DEBUG, VHOST_DATA,
+ "(%d) TX: pkt to local VM device id: (%d), vlan tag: %u.\n",
+ vdev->vid, dst_vdev->vid, *vlan_tag);
return 0;
}
tcp_hdr->cksum = get_psd_sum(l3_hdr, m->ol_flags);
}
+static inline void
+free_pkts(struct rte_mbuf **pkts, uint16_t n)
+{
+ while (n--)
+ rte_pktmbuf_free(pkts[n]);
+}
+
+static inline void __attribute__((always_inline))
+do_drain_mbuf_table(struct mbuf_table *tx_q)
+{
+ uint16_t count;
+
+ count = rte_eth_tx_burst(ports[0], tx_q->txq_id,
+ tx_q->m_table, tx_q->len);
+ if (unlikely(count < tx_q->len))
+ free_pkts(&tx_q->m_table[count], tx_q->len - count);
+
+ tx_q->len = 0;
+}
+
/*
- * This function routes the TX packet to the correct interface. This may be a local device
- * or the physical port.
+ * This function routes the TX packet to the correct interface. This
+ * may be a local device or the physical port.
*/
static inline void __attribute__((always_inline))
virtio_tx_route(struct vhost_dev *vdev, struct rte_mbuf *m, uint16_t vlan_tag)
{
struct mbuf_table *tx_q;
- struct rte_mbuf **m_table;
- unsigned len, ret, offset = 0;
+ unsigned offset = 0;
const uint16_t lcore_id = rte_lcore_id();
- struct virtio_net *dev = vdev->dev;
struct ether_hdr *nh;
if (unlikely(is_broadcast_ether_addr(&nh->d_addr))) {
struct vhost_dev *vdev2;
- TAILQ_FOREACH(vdev2, &vhost_dev_list, next) {
- virtio_xmit(vdev2->dev, vdev->dev, m);
+ TAILQ_FOREACH(vdev2, &vhost_dev_list, global_vdev_entry) {
+ virtio_xmit(vdev2, vdev, m);
}
goto queue2nic;
}
}
if (unlikely(vm2vm_mode == VM2VM_HARDWARE)) {
- if (unlikely(find_local_dest(dev, m, &offset, &vlan_tag) != 0)) {
+ if (unlikely(find_local_dest(vdev, m, &offset,
+ &vlan_tag) != 0)) {
rte_pktmbuf_free(m);
return;
}
}
- RTE_LOG(DEBUG, VHOST_DATA, "(%" PRIu64 ") TX: "
- "MAC address is external\n", dev->device_fh);
+ RTE_LOG_DP(DEBUG, VHOST_DATA,
+ "(%d) TX: MAC address is external\n", vdev->vid);
queue2nic:
/*Add packet to the port tx queue*/
tx_q = &lcore_tx_queue[lcore_id];
- len = tx_q->len;
nh = rte_pktmbuf_mtod(m, struct ether_hdr *);
if (unlikely(nh->ether_type == rte_cpu_to_be_16(ETHER_TYPE_VLAN))) {
if (m->ol_flags & PKT_TX_TCP_SEG)
virtio_tx_offload(m);
- tx_q->m_table[len] = m;
- len++;
+ tx_q->m_table[tx_q->len++] = m;
if (enable_stats) {
- dev_statistics[dev->device_fh].tx_total++;
- dev_statistics[dev->device_fh].tx++;
+ vdev->stats.tx_total++;
+ vdev->stats.tx++;
}
- if (unlikely(len == MAX_PKT_BURST)) {
- m_table = (struct rte_mbuf **)tx_q->m_table;
- ret = rte_eth_tx_burst(ports[0], (uint16_t)tx_q->txq_id, m_table, (uint16_t) len);
- /* Free any buffers not handled by TX and update the port stats. */
- if (unlikely(ret < len)) {
- do {
- rte_pktmbuf_free(m_table[ret]);
- } while (++ret < len);
+ if (unlikely(tx_q->len == MAX_PKT_BURST))
+ do_drain_mbuf_table(tx_q);
+}
+
+
+static inline void __attribute__((always_inline))
+drain_mbuf_table(struct mbuf_table *tx_q)
+{
+ static uint64_t prev_tsc;
+ uint64_t cur_tsc;
+
+ if (tx_q->len == 0)
+ return;
+
+ cur_tsc = rte_rdtsc();
+ if (unlikely(cur_tsc - prev_tsc > MBUF_TABLE_DRAIN_TSC)) {
+ prev_tsc = cur_tsc;
+
+ RTE_LOG_DP(DEBUG, VHOST_DATA,
+ "TX queue drained after timeout with burst size %u\n",
+ tx_q->len);
+ do_drain_mbuf_table(tx_q);
+ }
+}
+
+static inline void __attribute__((always_inline))
+drain_eth_rx(struct vhost_dev *vdev)
+{
+ uint16_t rx_count, enqueue_count;
+ struct rte_mbuf *pkts[MAX_PKT_BURST];
+
+ rx_count = rte_eth_rx_burst(ports[0], vdev->vmdq_rx_q,
+ pkts, MAX_PKT_BURST);
+ if (!rx_count)
+ return;
+
+ /*
+ * When "enable_retry" is set, here we wait and retry when there
+ * is no enough free slots in the queue to hold @rx_count packets,
+ * to diminish packet loss.
+ */
+ if (enable_retry &&
+ unlikely(rx_count > rte_vhost_avail_entries(vdev->vid,
+ VIRTIO_RXQ))) {
+ uint32_t retry;
+
+ for (retry = 0; retry < burst_rx_retry_num; retry++) {
+ rte_delay_us(burst_rx_delay_time);
+ if (rx_count <= rte_vhost_avail_entries(vdev->vid,
+ VIRTIO_RXQ))
+ break;
}
+ }
+
+ enqueue_count = rte_vhost_enqueue_burst(vdev->vid, VIRTIO_RXQ,
+ pkts, rx_count);
+ if (enable_stats) {
+ rte_atomic64_add(&vdev->stats.rx_total_atomic, rx_count);
+ rte_atomic64_add(&vdev->stats.rx_atomic, enqueue_count);
+ }
+
+ free_pkts(pkts, rx_count);
+}
- len = 0;
+static inline void __attribute__((always_inline))
+drain_virtio_tx(struct vhost_dev *vdev)
+{
+ struct rte_mbuf *pkts[MAX_PKT_BURST];
+ uint16_t count;
+ uint16_t i;
+
+ count = rte_vhost_dequeue_burst(vdev->vid, VIRTIO_TXQ, mbuf_pool,
+ pkts, MAX_PKT_BURST);
+
+ /* setup VMDq for the first packet */
+ if (unlikely(vdev->ready == DEVICE_MAC_LEARNING) && count) {
+ if (vdev->remove || link_vmdq(vdev, pkts[0]) == -1)
+ free_pkts(pkts, count);
}
- tx_q->len = len;
- return;
+ for (i = 0; i < count; ++i)
+ virtio_tx_route(vdev, pkts[i], vlan_tags[vdev->vid]);
}
+
/*
- * This function is called by each data core. It handles all RX/TX registered with the
- * core. For TX the specific lcore linked list is used. For RX, MAC addresses are compared
- * with all devices in the main linked list.
+ * Main function of vhost-switch. It basically does:
+ *
+ * for each vhost device {
+ * - drain_eth_rx()
+ *
+ * Which drains the host eth Rx queue linked to the vhost device,
+ * and deliver all of them to guest virito Rx ring associated with
+ * this vhost device.
+ *
+ * - drain_virtio_tx()
+ *
+ * Which drains the guest virtio Tx queue and deliver all of them
+ * to the target, which could be another vhost device, or the
+ * physical eth dev. The route is done in function "virtio_tx_route".
+ * }
*/
static int
-switch_worker(__attribute__((unused)) void *arg)
+switch_worker(void *arg __rte_unused)
{
- struct virtio_net *dev = NULL;
- struct vhost_dev *vdev = NULL;
- struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
+ unsigned i;
+ unsigned lcore_id = rte_lcore_id();
+ struct vhost_dev *vdev;
struct mbuf_table *tx_q;
- const uint64_t drain_tsc = (rte_get_tsc_hz() + US_PER_S - 1) / US_PER_S * BURST_TX_DRAIN_US;
- uint64_t prev_tsc, diff_tsc, cur_tsc, ret_count = 0;
- unsigned ret, i;
- const uint16_t lcore_id = rte_lcore_id();
- const uint16_t num_cores = (uint16_t)rte_lcore_count();
- uint16_t rx_count = 0;
- uint16_t tx_count;
- uint32_t retry = 0;
RTE_LOG(INFO, VHOST_DATA, "Procesing on Core %u started\n", lcore_id);
- prev_tsc = 0;
tx_q = &lcore_tx_queue[lcore_id];
- for (i = 0; i < num_cores; i ++) {
+ for (i = 0; i < rte_lcore_count(); i++) {
if (lcore_ids[i] == lcore_id) {
tx_q->txq_id = i;
break;
}
while(1) {
- cur_tsc = rte_rdtsc();
- /*
- * TX burst queue drain
- */
- diff_tsc = cur_tsc - prev_tsc;
- if (unlikely(diff_tsc > drain_tsc)) {
-
- if (tx_q->len) {
- RTE_LOG(DEBUG, VHOST_DATA,
- "TX queue drained after timeout with burst size %u\n",
- tx_q->len);
-
- /*Tx any packets in the queue*/
- ret = rte_eth_tx_burst(ports[0], (uint16_t)tx_q->txq_id,
- (struct rte_mbuf **)tx_q->m_table,
- (uint16_t)tx_q->len);
- if (unlikely(ret < tx_q->len)) {
- do {
- rte_pktmbuf_free(tx_q->m_table[ret]);
- } while (++ret < tx_q->len);
- }
-
- tx_q->len = 0;
- }
-
- prev_tsc = cur_tsc;
-
- }
+ drain_mbuf_table(tx_q);
/*
* Inform the configuration core that we have exited the
lcore_info[lcore_id].dev_removal_flag = ACK_DEV_REMOVAL;
/*
- * Process devices
+ * Process vhost devices
*/
- TAILQ_FOREACH(vdev, &lcore_info[lcore_id].vdev_list, next) {
- uint64_t fh;
-
- dev = vdev->dev;
- fh = dev->device_fh;
-
+ TAILQ_FOREACH(vdev, &lcore_info[lcore_id].vdev_list,
+ lcore_vdev_entry) {
if (unlikely(vdev->remove)) {
unlink_vmdq(vdev);
vdev->ready = DEVICE_SAFE_REMOVE;
continue;
}
- if (likely(vdev->ready == DEVICE_RX)) {
- /*Handle guest RX*/
- rx_count = rte_eth_rx_burst(ports[0],
- vdev->vmdq_rx_q, pkts_burst, MAX_PKT_BURST);
-
- if (rx_count) {
- /*
- * Retry is enabled and the queue is full then we wait and retry to avoid packet loss
- * Here MAX_PKT_BURST must be less than virtio queue size
- */
- if (enable_retry && unlikely(rx_count > rte_vring_available_entries(dev, VIRTIO_RXQ))) {
- for (retry = 0; retry < burst_rx_retry_num; retry++) {
- rte_delay_us(burst_rx_delay_time);
- if (rx_count <= rte_vring_available_entries(dev, VIRTIO_RXQ))
- break;
- }
- }
- ret_count = rte_vhost_enqueue_burst(dev, VIRTIO_RXQ, pkts_burst, rx_count);
- if (enable_stats) {
- rte_atomic64_add(
- &dev_statistics[fh].rx_total_atomic,
- rx_count);
- rte_atomic64_add(
- &dev_statistics[fh].rx_atomic,
- ret_count);
- }
- while (likely(rx_count)) {
- rx_count--;
- rte_pktmbuf_free(pkts_burst[rx_count]);
- }
-
- }
- }
+ if (likely(vdev->ready == DEVICE_RX))
+ drain_eth_rx(vdev);
- if (likely(!vdev->remove)) {
- /* Handle guest TX*/
- tx_count = rte_vhost_dequeue_burst(dev, VIRTIO_TXQ, mbuf_pool, pkts_burst, MAX_PKT_BURST);
- /* If this is the first received packet we need to learn the MAC and setup VMDQ */
- if (unlikely(vdev->ready == DEVICE_MAC_LEARNING) && tx_count) {
- if (vdev->remove || (link_vmdq(vdev, pkts_burst[0]) == -1)) {
- while (tx_count)
- rte_pktmbuf_free(pkts_burst[--tx_count]);
- }
- }
- for (i = 0; i < tx_count; ++i) {
- virtio_tx_route(vdev, pkts_burst[i],
- vlan_tags[(uint16_t)dev->device_fh]);
- }
- }
+ if (likely(!vdev->remove))
+ drain_virtio_tx(vdev);
}
}
* of dev->remove=1 which can cause an infinite loop in the rte_pause loop.
*/
static void
-destroy_device (volatile struct virtio_net *dev)
+destroy_device(int vid)
{
- struct vhost_dev *vdev;
+ struct vhost_dev *vdev = NULL;
int lcore;
- dev->flags &= ~VIRTIO_DEV_RUNNING;
-
- vdev = (struct vhost_dev *)dev->priv;
+ TAILQ_FOREACH(vdev, &vhost_dev_list, global_vdev_entry) {
+ if (vdev->vid == vid)
+ break;
+ }
+ if (!vdev)
+ return;
/*set the remove flag. */
vdev->remove = 1;
while(vdev->ready != DEVICE_SAFE_REMOVE) {
rte_pause();
}
- TAILQ_REMOVE(&lcore_info[vdev->coreid].vdev_list, vdev, next);
- TAILQ_REMOVE(&vhost_dev_list, vdev, next);
+ TAILQ_REMOVE(&lcore_info[vdev->coreid].vdev_list, vdev,
+ lcore_vdev_entry);
+ TAILQ_REMOVE(&vhost_dev_list, vdev, global_vdev_entry);
+
/* Set the dev_removal_flag on each lcore. */
RTE_LCORE_FOREACH_SLAVE(lcore)
lcore_info[vdev->coreid].device_num--;
RTE_LOG(INFO, VHOST_DATA,
- "(%" PRIu64 ") Device has been removed from data core\n",
- dev->device_fh);
+ "(%d) device has been removed from data core\n",
+ vdev->vid);
rte_free(vdev);
}
* and the allocated to a specific data core.
*/
static int
-new_device (struct virtio_net *dev)
+new_device(int vid)
{
int lcore, core_add = 0;
uint32_t device_num_min = num_devices;
vdev = rte_zmalloc("vhost device", sizeof(*vdev), RTE_CACHE_LINE_SIZE);
if (vdev == NULL) {
- RTE_LOG(INFO, VHOST_DATA, "(%"PRIu64") Couldn't allocate memory for vhost dev\n",
- dev->device_fh);
+ RTE_LOG(INFO, VHOST_DATA,
+ "(%d) couldn't allocate memory for vhost dev\n",
+ vid);
return -1;
}
- vdev->dev = dev;
- dev->priv = vdev;
+ vdev->vid = vid;
- TAILQ_INSERT_TAIL(&vhost_dev_list, vdev, next);
- vdev->vmdq_rx_q
- = dev->device_fh * queues_per_pool + vmdq_queue_base;
+ TAILQ_INSERT_TAIL(&vhost_dev_list, vdev, global_vdev_entry);
+ vdev->vmdq_rx_q = vid * queues_per_pool + vmdq_queue_base;
/*reset ready flag*/
vdev->ready = DEVICE_MAC_LEARNING;
}
vdev->coreid = core_add;
- TAILQ_INSERT_TAIL(&lcore_info[vdev->coreid].vdev_list, vdev, next);
+ TAILQ_INSERT_TAIL(&lcore_info[vdev->coreid].vdev_list, vdev,
+ lcore_vdev_entry);
lcore_info[vdev->coreid].device_num++;
- /* Initialize device stats */
- memset(&dev_statistics[dev->device_fh], 0, sizeof(struct device_statistics));
-
/* Disable notifications. */
- rte_vhost_enable_guest_notification(dev, VIRTIO_RXQ, 0);
- rte_vhost_enable_guest_notification(dev, VIRTIO_TXQ, 0);
- dev->flags |= VIRTIO_DEV_RUNNING;
+ rte_vhost_enable_guest_notification(vid, VIRTIO_RXQ, 0);
+ rte_vhost_enable_guest_notification(vid, VIRTIO_TXQ, 0);
- RTE_LOG(INFO, VHOST_DATA, "(%"PRIu64") Device has been added to data core %d\n", dev->device_fh, vdev->coreid);
+ RTE_LOG(INFO, VHOST_DATA,
+ "(%d) device has been added to data core %d\n",
+ vid, vdev->coreid);
return 0;
}
struct vhost_dev *vdev;
uint64_t tx_dropped, rx_dropped;
uint64_t tx, tx_total, rx, rx_total;
- uint32_t device_fh;
const char clr[] = { 27, '[', '2', 'J', '\0' };
const char top_left[] = { 27, '[', '1', ';', '1', 'H','\0' };
sleep(enable_stats);
/* Clear screen and move to top left */
- printf("%s%s", clr, top_left);
-
- printf("\nDevice statistics ====================================");
+ printf("%s%s\n", clr, top_left);
+ printf("Device statistics =================================\n");
- TAILQ_FOREACH(vdev, &vhost_dev_list, next) {
- device_fh = vdev->dev->device_fh;
- tx_total = dev_statistics[device_fh].tx_total;
- tx = dev_statistics[device_fh].tx;
+ TAILQ_FOREACH(vdev, &vhost_dev_list, global_vdev_entry) {
+ tx_total = vdev->stats.tx_total;
+ tx = vdev->stats.tx;
tx_dropped = tx_total - tx;
- rx_total = rte_atomic64_read(
- &dev_statistics[device_fh].rx_total_atomic);
- rx = rte_atomic64_read(
- &dev_statistics[device_fh].rx_atomic);
+
+ rx_total = rte_atomic64_read(&vdev->stats.rx_total_atomic);
+ rx = rte_atomic64_read(&vdev->stats.rx_atomic);
rx_dropped = rx_total - rx;
- printf("\nStatistics for device %"PRIu32" ------------------------------"
- "\nTX total: %"PRIu64""
- "\nTX dropped: %"PRIu64""
- "\nTX successful: %"PRIu64""
- "\nRX total: %"PRIu64""
- "\nRX dropped: %"PRIu64""
- "\nRX successful: %"PRIu64"",
- device_fh,
- tx_total,
- tx_dropped,
- tx,
- rx_total,
- rx_dropped,
- rx);
+ printf("Statistics for device %d\n"
+ "-----------------------\n"
+ "TX total: %" PRIu64 "\n"
+ "TX dropped: %" PRIu64 "\n"
+ "TX successful: %" PRIu64 "\n"
+ "RX total: %" PRIu64 "\n"
+ "RX dropped: %" PRIu64 "\n"
+ "RX successful: %" PRIu64 "\n",
+ vdev->vid,
+ tx_total, tx_dropped, tx,
+ rx_total, rx_dropped, rx);
}
- printf("\n======================================================\n");
+
+ printf("===================================================\n");
+ }
+}
+
+static void
+unregister_drivers(int socket_num)
+{
+ int i, ret;
+
+ for (i = 0; i < socket_num; i++) {
+ ret = rte_vhost_driver_unregister(socket_files + i * PATH_MAX);
+ if (ret != 0)
+ RTE_LOG(ERR, VHOST_CONFIG,
+ "Fail to unregister vhost driver for %s.\n",
+ socket_files + i * PATH_MAX);
}
}
sigint_handler(__rte_unused int signum)
{
/* Unregister vhost driver. */
- int ret = rte_vhost_driver_unregister((char *)&dev_basename);
- if (ret != 0)
- rte_exit(EXIT_FAILURE, "vhost driver unregister failure.\n");
+ unregister_drivers(nb_sockets);
+
exit(0);
}
}
/*
- * Main function, does initialisation and calls the per-lcore functions. The CUSE
- * device is also registered here to handle the IOCTLs.
+ * Main function, does initialisation and calls the per-lcore functions.
*/
int
main(int argc, char *argv[])
{
unsigned lcore_id, core_id = 0;
unsigned nb_ports, valid_num_ports;
- int ret;
+ int ret, i;
uint8_t portid;
static pthread_t tid;
char thread_name[RTE_MAX_THREAD_NAME_LEN];
+ uint64_t flags = 0;
signal(SIGINT, sigint_handler);
/* Get the number of physical ports. */
nb_ports = rte_eth_dev_count();
- if (nb_ports > RTE_MAX_ETHPORTS)
- nb_ports = RTE_MAX_ETHPORTS;
/*
* Update the global var NUM_PORTS and global array PORTS
"Cannot initialize network ports\n");
}
- /* Initialize device stats */
- memset(&dev_statistics, 0, sizeof(dev_statistics));
-
/* Enable stats if the user option is set. */
if (enable_stats) {
ret = pthread_create(&tid, NULL, (void *)print_stats, NULL);
snprintf(thread_name, RTE_MAX_THREAD_NAME_LEN, "print-stats");
ret = rte_thread_setname(tid, thread_name);
if (ret != 0)
- RTE_LOG(ERR, VHOST_CONFIG,
+ RTE_LOG(DEBUG, VHOST_CONFIG,
"Cannot set print-stats name\n");
}
if (mergeable == 0)
rte_vhost_feature_disable(1ULL << VIRTIO_NET_F_MRG_RXBUF);
- /* Register vhost(cuse or user) driver to handle vhost messages. */
- ret = rte_vhost_driver_register((char *)&dev_basename);
- if (ret != 0)
- rte_exit(EXIT_FAILURE, "vhost driver register failure.\n");
+ if (client_mode)
+ flags |= RTE_VHOST_USER_CLIENT;
+
+ if (dequeue_zero_copy)
+ flags |= RTE_VHOST_USER_DEQUEUE_ZERO_COPY;
+
+ /* Register vhost user driver to handle vhost messages. */
+ for (i = 0; i < nb_sockets; i++) {
+ ret = rte_vhost_driver_register
+ (socket_files + i * PATH_MAX, flags);
+ if (ret != 0) {
+ unregister_drivers(i);
+ rte_exit(EXIT_FAILURE,
+ "vhost driver register failure.\n");
+ }
+ }
rte_vhost_driver_callback_register(&virtio_net_device_ops);
- /* Start CUSE session. */
rte_vhost_driver_session_start();
return 0;
git.droids-corp.org / dpdk.git / blobdiff